digitalocean/benchmark-harness

forked from OpenRouterTeam/benchmark-harness

Open original ↗

Captured source

source ↗
published Sep 17, 2026seen 3wcaptured 3whttp 200method plain

digitalocean/benchmark-harness

Description: OpenRouter TypeScript harness for reproducible LLM benchmarks and evaluations.

License: Apache-2.0

Stars: 1

Forks: 0

Open issues: 1

Created: 2026-09-17T17:14:48Z

Pushed: 2026-09-17T17:16:03Z

Default branch: main

Fork: yes

Parent repository: OpenRouterTeam/benchmark-harness

Archived: no

README:

OpenRouter Benchmark Harness

OpenRouter's internal benchmarking harness, externalized for transparency. We port benchmarks here so we can run them scalably on our infrastructure and iterate quickly.

bun install
OPENROUTER_API_KEY=... bun run bench -- --benchmark gpqa_diamond --model openai/gpt-4o-mini --limit 5

See [CONTRIBUTING.md](CONTRIBUTING.md) before proposing changes. Report security issues privately as described in [SECURITY.md](SECURITY.md).